Skip to content
AI News HubLIVE
Original source2 min read

Cognitively Constrained Partners for Zero-Shot Coordination in Real-Time Partitioned Control

Summary

The paper proposes training teaming agents against cognitively constrained simulated partners whose diversity comes from human-grounded physiological constraints such as reaction delays and perceptual limits, rather than reward shaping or historical checkpoints. In a modified Lunar Lander environment, preliminary evidence suggests these partners behave more like real people, and agents trained against them match the strongest cross-play baselines while being the only ones whose performance is independent of how training partners were generated. The authors also describe a human-participant study designed to compare directly against cross-play.

SourcearXiv Machine LearningAuthor: Ash Simmons, George De Ath, Richard M. Everson
Cognitively Constrained Partners for Zero-Shot Coordination in Real-Time Partitioned Control
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 22 Oct 2026]

Title:Cognitively Constrained Partners for Zero-Shot Coordination in Real-Time Partitioned Control

View a PDF of the paper titled Cognitively Constrained Partners for Zero-Shot Coordination in Real-Time Partitioned Control, by Ash Simmons and 2 other authors

View PDF HTML (experimental)

Abstract:Effective human-machine teaming requires agents that coordinate with unpredictable human partners. Reinforcement learning from live human feedback or large behavioural datasets is expensive, while purely simulated training overfits to artificial conventions and fails at Zero-Shot Coordination with real people. We propose a framework for training teaming agents against Cognitively Constrained Partners: simulated partners whose diversity emerges from procedural constraints grounded in human physiological literature, specifically reaction delays and perceptual limitations, rather than from reward shaping or historical training checkpoints. In a modified Lunar Lander environment, we report preliminary evidence that these partners play more like real people than unconstrained agents do, and that agents trained against them match the strongest cross-play baselines while being the only ones whose performance does not depend on how their training partners were generated. We also describe a human-participant study designed so that its rankings can be compared directly against cross-play, testing how well that standard evaluation predicts real human-agent teaming.

Comments: 30 pages, 6 figures, 5 tables. Accepted at the NeurIPS 2026 Workshop on Human-AI Coevolution: Measuring Human-Agent Teams in the Agentic Era

Subjects:

Machine Learning (cs.LG); Human-Computer Interaction (cs.HC)

Cite as: arXiv:2610.31726 [cs.LG]

(or arXiv:2610.31726v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2610.31726

arXiv-issued DOI via DataCite

Submission history

From: Ash Simmons [view email] [v1] Thu, 22 Oct 2026 13:53:38 UTC (482 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Cognitively Constrained Partners for Zero-Shot Coordination in Real-Time Partitioned Control, by Ash Simmons and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-10

Change to browse by:

cs cs.HC

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Partner diversity emerges from procedural constraints grounded in human physiology, notably reaction delays and perceptual limitations
  • In a modified Lunar Lander environment, these partners play more like real people than unconstrained agents
  • Agents trained against them match the strongest cross-play baselines and are uniquely insensitive to how training partners were generated
  • A human-participant study is designed so its rankings can be compared directly with cross-play results

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Agents